NVIDIA

Nvidia Nemotron 70b

Generally availableOpen weights16K context

Summary

Nvidia Nemotron 70b is an open-weight language model from NVIDIA, released on 15 Apr 2025. It accepts text and generates text, with a 16K-token context window and up to 8K output tokens per response.

Nemotron model for efficient reasoning, coding, and specialized AI agents

Last verified 18 Nov 2026. Every figure on this page links to its source.

Specifications

DeveloperNVIDIA
Release date15 Apr 2025 [models.dev]
StatusGenerally available [models.dev]
WeightsOpen weights [models.dev]
Context window16K (16,384 tokens) [models.dev]
Max output8K tokens [models.dev]
InputText [models.dev]
OutputText [models.dev]
Reasoning modeNo [models.dev]
Tool callingNo [models.dev]
Structured outputNo [models.dev]

Nvidia Nemotron 70b API pricing by provider

USD per million tokens. Sorted by input price.

We do not currently track a paid API listing for this model.

Frequently asked questions

What is the context window of Nvidia Nemotron 70b?

Nvidia Nemotron 70b has a context window of 16,384 tokens (16K) and can generate up to 8,192 tokens in a single response, according to models.dev.

Is Nvidia Nemotron 70b open source?

Nvidia Nemotron 70b is an open-weight model. Check the license terms before commercial use.

When was Nvidia Nemotron 70b released?

NVIDIA released Nvidia Nemotron 70b on 15 Apr 2025, according to models.dev.

Similar models from other labs

Comparable on output type, weights, release date, price and context window. Prices are the lowest listed, USD per million tokens.

ModelLabReleasedContextInput $/1MOutput $/1MWeights
Aya Vision 32BCohere4 Mar 202516K––Open
Phi 4Microsoft10 Jan 202516K$0.07$0.14Open
MinerU2.5 2509 1.2BOpendatalab17 Sept 202516K––Open
Llama 3.3 70B EuryaleSao10k18 Dec 202420K––Open
Skyfall 36B V2Thedrummer10 Mar 202533K$0.55$0.80Open
Qwen 3 Embedding 4BAlibaba (Qwen)5 Jun 202533K$0.01–Open

Change history

  • Context window changed from 131K to 16K
  • Tool calling changed from yes to no
  • Name changed from Llama 3.1 Nemotron 70B Instruct (Deep Infra) to Nvidia Nemotron 70b
  • Tool calling changed from no to yes
  • Name changed from Nvidia Nemotron 70b to Llama 3.1 Nemotron 70B Instruct (Deep Infra)
  • Context window changed from 16K to 131K
  • Name changed from Llama 3.1 Nemotron 70B Instruct (Deep Infra) to Nvidia Nemotron 70b
  • Context window changed from 131K to 16K
  • Tool calling changed from yes to no
  • Tool calling changed from no to yes
  • Context window changed from 16K to 131K
  • Name changed from Nvidia Nemotron 70b to Llama 3.1 Nemotron 70B Instruct (Deep Infra)
  • Tool calling changed from yes to no
  • Name changed from Llama 3.1 Nemotron 70B Instruct (Deep Infra) to Nvidia Nemotron 70b
  • Context window changed from 131K to 16K
  • Context window changed from 16K to 131K
  • Tool calling changed from no to yes
  • Name changed from Nvidia Nemotron 70b to Llama 3.1 Nemotron 70B Instruct (Deep Infra)
  • Name changed from Llama 3.1 Nemotron 70B Instruct (Deep Infra) to Nvidia Nemotron 70b
  • Context window changed from 131K to 16K
  • Tool calling changed from yes to no
  • Context window changed from 16K to 131K
  • Tool calling changed from no to yes
  • Name changed from Nvidia Nemotron 70b to Llama 3.1 Nemotron 70B Instruct (Deep Infra)
  • Tool calling changed from yes to no

Sources